© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4955
    Prev
    Next
    INDEX
    Explanations

    sentences that refer to previously presented ideas

    oai_token-act-pair · gemini-2.0-flash

    learn

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.84
    :✨
    -0.76
    setVerticalGroup
    -0.69
     resourceCulture
    -0.69
    رشف
    -0.67
    ReusableCell
    -0.64
    SBATCH
    -0.63
     jScrollPane
    -0.63
    Bronnen
    -0.62
    UserScript
    -0.62
    POSITIVE LOGITS
     learned
    0.91
     learn
    0.82
     learnt
    0.81
     Learned
    0.78
     we
    0.77
     learning
    0.75
     apprend
    0.73
    We
    0.72
    learned
    0.69
     Learn
    0.68
    Activations Density 1.125%

    No Known Activations